Upload mtdna_classifier.py

mtdna_classifier.py

@@ -135,18 +135,18 @@ def load_haplogroup_mapping(csv_path):
 
 # Function to extract haplogroup from the text
 def extract_haplogroup(text):
-    # 1. Try to find a haplogroup preceded by the word "haplogroup"
     match = re.search(r'\bhaplogroup\s+([A-Z][0-9a-z]*)\b', text)
     if match:
-      return re.match(r'^[A-Z][0-9]*', match.group(1)).group(0)
-        #return match.group(1)  # This is the actual haplogroup code like U5b1
-
-    # 2. Fallback: try to find isolated uppercase-letter haplogroup codes
+        submatch = re.match(r'^[A-Z][0-9]*', match.group(1))
+        if submatch:
+            return submatch.group(0)
+        else:
+            return match.group(1)  # fallback
     fallback = re.search(r'\b([A-Z][0-9a-z]{1,5})\b', text)
     if fallback:
         return fallback.group(1)
+    return None
 
-    return None  # If nothing found
 
 # Function to extract location based on NER
 def extract_location(text):